1. A Framework for Multi-Omic Prediction of Treatment Response to Biologic Therapy for Psoriasis 
Amy C. Foulkes, David S. Watson, Daniel F. Carr, John G. Kenny, Timothy Slidel, Richard Parslew, Munir Pirmohamed, Simon Anders, Nick J. Reynolds, Christopher E.M. Griffiths, Richard B. Warren, Michael R. Barnes 
Journal of Investigative Dermatology 
Volume 139, Issue 1, Pages (January 2019)
DOI: /j.jid
Copyright © 2018 The Authors Terms and Conditions

2. Figure 1
Study overview. Participants were assessed at baseline, week 1, and week 12 of therapy. Participant sampling comprised blood testing, urine collection, lesional and nonlesional skin biopsies (from photoprotected sites on the lower back/buttock, from the edge of plaques, and at a minimum distance from previous biopsy sites). RNA sequencing was conducted on mRNA from blood and lesional and nonlesional skin and microRNA (miRNA) from blood. Proteomic assessment was conducted on serum. seq, sequencing; Wk, week.
Journal of Investigative Dermatology  , DOI: ( /j.jid )
Copyright © 2018 The Authors Terms and Conditions

3. Figure 2
Differential expression of mRNA, miRNA, and protein across time and across tissue. (a) The number of biomolecules declared differentially expressed between responders and nonresponders at a 10% FDR for each tissue, time point, and platform. The number of tests vary between platforms: mRNA = 19,304, miRNA = 3,632, and protein = 1,129. (b) Model metrics for random forests; we report mean (SD) predictive error and number of features retained after recursive feature elimination for each data platform and response type. Continuous response models were evaluated using RMSE, and categorical models were tuned with cross-entropy loss. Asterisks denote the top performing data platform for each class of random forests. FDR, false discovery rate; RMSE, root-mean-square error; SD; standard deviation; wk, week.
Journal of Investigative Dermatology  , DOI: ( /j.jid )
Copyright © 2018 The Authors Terms and Conditions

4. Figure 3
Top upstream regulators across genes differentially expressed in relation to etanercept differential expression (P < 0.05) response in psoriasis. The top 30 upstream regulators are shown. The prediction of activation state is based on the global direction of changes of genes with differential expression P < The nominal limit of significance (z-score < –2 or > 2) is indicated by the activation z-score color scale. wk, week.
Journal of Investigative Dermatology  , DOI: ( /j.jid )
Copyright © 2018 The Authors Terms and Conditions

5. Figure 4
Concordance of platforms at prediction of PASI75. (a) Heatmap depicting the concordance of cluster assignments across platforms as determined by supervised methods. (b) Box plots show the distribution of cross-validated over 10 folds for a series of random forests models with recursive feature elimination trained to predict the change in PASI using only baseline samples. Lower RMSE values indicate more predictive models. PASI, Psoriasis Area and Severity Index; PASI75, reduction of Psoriasis Area and Severity Index by at least 75% from baseline; RMSE, root-mean-square error.
Journal of Investigative Dermatology  , DOI: ( /j.jid )
Copyright © 2018 The Authors Terms and Conditions